HEADPOSE ESTIMATION USING FACIAL LANDMARKS AND OPENCV

WHAT IS IT?

There are three major steps: Face detection: A face detector is adopted to provide a face box containing a human face. Then the face box is expanded and transformed to a square to suit the needs of later steps. Facial landmark detection: A custom trained facial landmark detector based on TensorFlow is responsible for output 68 facial landmarks. Pose estimation: Once we got the 68 facial landmarks, a mutual PnP algorithms is adopted to calculate the pose. The marks is detected frame by frame, which result in small variance between adjacent frames. This makes the pose unstable. A Kalman filter is used to solve this problem, one can draw the original pose to observe the difference.

HOW TO USE?

To run the script python run.py -input test.jpg  -gpu_frac 0 For help options - python run.py -h

usage:

run.py [-h] [-input INPUT] [-gpu_frac GPU_FRAC]

optional arguments: -h, --help                                 show this help message and exit -input         INPUT                   mention input image -gpu_frac   GPU_FRAC          mention gpu fraction to use

WHAT ARE THE REQUIREMENTS?

To get all the requirements and dependencies installed run the command For GPU - pip install -r gpu_requirements.txt For CPU - pip install -r cpu_requirements.txt